ARTMAP: supervised real-time learning and classification of nonstationary data by a self-organizing neural network

By Gail A. Carpenter, Stephen Grossberg, John H. Reynolds. 1991

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Memory Efficient Experience Replay for Streaming Learning (2018, background): “ARTMAP networks [11], [12], [13], [71] are another approach and they learn faster.”
Lifelong Machine Learning with Deep Streaming Linear Discriminant Analysis (2019, methodology): “There have been shallow neural networks designed for streaming learning, including ARTMAP networks [7, 8, 49]; however, ARTMAP is sensitive to the order in which training data is presented and it is not capable of representation learning.”
Adaptive resonance theory (1997, background): “ARTMAP match tracking [37].”
Distributed Intelligent Energy Management System for a Single-Phase High-Frequency AC Microgrid (2007, background): “An intelligent energy management system is thus required which enables short-term energy allocation scheduling at minimum costs based on power generation and load demand [7].”
Connectionist modelling in psychology: A localist manifesto (2000, methodology): “This idea is strikingly similar to learning of associations between locally represented entities through projections to and from a maplayer (e.g., ARTMAP; Carpenter et al. 1991).”
Survey of clustering algorithms (2005, unknown): “Use crossover (two-point crossover) and mutation (bit-wise mutation) operator to generate offspring from the individuals chosen in step 2).”
CARTMAP: a neural network method for automated feature selection in financial time series forecasting (2012, methodology): “There are three basic steps to CART- MAP: (1) use Fuzzy ART [8] to cluster the features by similarity, generating a fixed number of clusters; (2) select at most one feature per feature cluster; (3) train ARTMAP on those selected features.”
A survey on concept drift adaptation (2014, background): “Setting these parameters requires a tradeoff between stability and sensitivity [Carpenter et al. 1991b].”
Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multidimensional maps (1992, methodology): “The first ARTMAP system (Carpenter, Grossberg, and Reynolds, 1991) was used to classify binary vectors.”
40 years of cognitive architectures: core cognitive abilities and practical applications (2018, unknown): “Conclusion Overall, visual attention is largely overlooked in cognitive architectures research with the exception of the biologically plausible visual models (e.g. ART) and the architectures that specifically focus on vision research (ARCADIA, STAR).14 This is surprising because strong theoretical a”
Neural Networks in R Using the Stuttgart Neural Network Simulator: RSNNS (2012, background): “Network architectures implemented in SNNS contain multi-layer perceptrons (MLP, Rosen-blatt 1958), recurrent Elman-, and Jordan networks (Elman 1990; Jordan 1986), radial basis function networks (RBF, Poggio and Girosi 1989), RBF with dynamic decay adjustment (Berthold and Diamond 1995; Hudak 1993),”
Supervised learning of fuzzy ARTMAP neural networks through particle swarm optimization (2007, methodology): “ARTMAP refers to a family of neural network architectures based on Adaptive Resonance Theory (ART) [4] that is capable of fast, stable, on-line, unsupervised or supervised, incremental learning, classification, and prediction [6] [7].”
Biased ART: A neural architecture that shifts attention toward previously disregarded features following an incorrect prediction (2010, unknown): “:3) must rise in order to correct the error is called match tracking (Carpenter, Grossberg, & Reynolds, 1991).”